---

Prepared by:
Deepthi Joshi
Saumya Sonkar
Saumya Srivastava
Shazia ahamad

---

[attachment=6505]

---

INTRODUCTION

1.1 PROBLEM DEFINITION

1. To implement the concept of Face Recognition.
2. To design an Human-Computer-Interactive-Interface implementing Face Recognition concept using JAVA.

1.2 PROPOSED SOLUTION

To develop a software that provide authentication by capturing the image of the user (say Employee) and comparing it with samples available in its database. If input image matches the image samples available with the software database then the user is valid else invalid.

The Software being developed has been named as CONNOISSEUR-the Expert Judge, since we visualize the software to be the best judge to identify and authenticate a user on check.

1.3 INTRODUCTION TO FACE RECOGNITION SYSTEMS

Anyone who has seen the TV show "Las Vegas" has seen facial recognition software in action. In any given episode, the security department at the fictional Montecito Hotel and Casino uses its video surveillance system to pull an image of a card counter, thief or blacklisted individual. It then runs that image through the database to find a match and identify the person. By the end of the hour, all bad guys are escorted from the casino or thrown in jail. But what looks so easy on TV doesn't always translate as well in the real world.
In 2001, the Tampa Police Department installed police cameras equipped with facial recognition technology in their Ybor City nightlife district in an attempt to cut down on crime in the area. The system failed to do the job, and it was scrapped in 2003 due to ineffectiveness. People in the area were seen wearing masks and making obscene gestures, prohibiting the cameras from getting a clear enough shot to identify anyone.
Boston's Logan Airport also ran two separate tests of facial recognition systems at its security checkpoints using volunteers. Over a three month period, the results were disappointing. According to the Electronic Privacy Information Center, the system only had a 61.4 percent accuracy rate, leading airport officials to pursue other security options.
Humans have always had the innate ability to recognize and distinguish between faces, yet computers only recently have shown the same ability. In the mid 1960s, scientists began work on using the computer to recognize human faces. Since then, facial recognition software has come a long way.
In this article, we will look at the history of facial recognition systems, the changes that are being made to enhance their capabilities and how governments and private companies use (or plan to use) them.

TECHNIQUES

Traditional
Some facial recognition algorithms identify faces by extracting landmarks, or features, from an image of the subject's face. For example, an algorithm may analyze the relative position, size, and/or shape of the eyes, nose, cheekbones, and jaw. These features are then used to search for other images with matching features.[2] Other algorithms normalize a gallery of face images and then compress the face data, only saving the data in the image that is useful for face detection. A probe image is then compared with the face data.[3] One of the earliest successful systems[4] is based on template matching techniques[5] applied to a set of salient facial features, providing a sort of compressed face representation.
Recognition algorithms can be divided into two main approaches, geometric, which looks at distinguishing features or photometric, which is a statistical approach that distill an image into values and comparing the values with templates to eliminate variances.
Popular recognition algorithms include Principal Component Analysis with eigenface, Linear Discriminate Analysis, Elastic Bunch Graph Matching fisherface, the Hidden Markov model, and the neuronal motivated dynamic page link matching.
3-D
A newly emerging trend, claimed to achieve previously unseen accuracies, is three-dimensional face recognition. This technique uses 3-D sensors to capture information about the shape of a face. This information is then used to identify distinctive features on the surface of a face, such as the contour of the eye sockets, nose, and chin.

One advantage of 3-D facial recognition is that it is not affected by changes in lighting like other techniques. It can also identify a face from a range of viewing angles, including a profile view.

Even a perfect 3D matching technique could be sensitive to expressions. For that goal a group at the Technion applied tools from metric geometry to treat expressions as isometries.

Skin Texture Analysis

Another emerging trend uses the visual details of the skin, as captured in standard digital or scanned images. This technique, called skin texture analysis, turns the unique lines, patterns, and spots apparent in a person’s skin into a mathematical space.

Tests have shown that with the addition of skin texture analysis, performance in recognizing faces can increase 20 to 25 percent.
Comparative study

Among the different biometric techniques, facial recognition may not be the most reliable and efficient. However, one key advantage is that it does not require aid (or consent) from the test subject. Properly designed systems installed in airports, multiplexes, and other public places can identify individuals among the crowd. Other biometrics like fingerprints, iris scans, and speech recognition cannot perform this kind of mass identification. However, questions have been raised on the effectiveness of facial recognition software in cases of railway and airport security.

[attachment=11011]
Biometrics Systems
Biometric Systems Segment Organization
Introduction
System architecture
Introduction
 Biometrics
 Engineering Definition and Approaches
 Definition, Criteria for Selection
 Survey of Current Biometrics and Relative Properties
 Introduction to socio-legal implications and issues
 Recap –
Identification in the 21st Century
 Dispersion of people from their “Natural ID Centers”
 Social units have grown to tens of thousands or millions/billions.
 Need to assure associations of identity with end-to-end transactions without physical presence
 Project your presence (ID) instantly, accurately, and securely across any distance
Identification Methods
 We need to achieve this recognition automatically in order to authenticate our identity.
 Identity is not a passive thing, but associated with an act or intent involving the person with that identity
 Seek a manageable engineering definition.
Biometric Identification
 Pervasive use of biometric ID is enabled by automated systems
 Enabled by inexpensive embedded computing and sensing.
 Computer controlled acquisition, processing, storage, and matching using biometrics.
 Biometric systems are one solution to increasing demand for strong authentication of actions in a global environment.
 Biometrics tightly binds an event to an individual
 A biometric can not be lost or forgotten, however a biometric must be enrolled.
What is an Automated Biometric System?
 An automated biometric system uses biological, physiological or behavioral characteristics to automatically authenticate the identity of an individual based on a previous enrollment event.
 For the purposes of this course, human identity authentication is the focus. But in general, this need not necessarily be the case.
Characteristics of a Useful Biometric
 If a biological, physiological, or behavioral characteristic has the following properties…
 Universality
 Uniqueness
 Permanence
 Collectability
….then it can potentially serve as a biometric for a given application.
Useful Biometrics
 1. Universality
 Universality: Every person should possess this characteristic
 In practice, this may not be the case
 Otherwise, population of nonuniversality must be small < 1%
 2. Uniqueness
 Uniqueness: No two individuals possess the same characteristic.
 Genotypical – Genetically linked (e.g. identical twins will have same biometric)
 Phenotypical – Non-genetically linked, different perhaps even on same individual
 Establishing uniqueness is difficult to prove analytically
 May be unique, but “uniqueness” must be distinguishable
 3. Permanence
 Permanence: The characteristic does not change in time, that is, it is time invariant
 At best this is an approximation
 Degree of permanence has a major impact on the system design and long term operation of biometrics. (e.g. enrollment, adaptive matching design, etc.)
 Long vs. short-term stability
 4. Collectability
 Collectability: The characteristic can be quantitatively measured.
 In practice, the biometric collection must be:
 Non-intrusive
 Reliable and robust
 Cost effective for a given application
Current/Potential Biometrics
 Voice
 Infrared facial thermography
 Fingerprints
 Face
 Iris
 Ear
 EKG, EEG
 Odor
 Gait
 Keystroke dynamics
 DNA
 Signature
 Retinal scan
 Hand & finger geometry
 Subcutaneous blood vessel imaging
System-Level Criteria
 Our four criteria were for evaluation of the viability of a chosen characteristic for use as a biometric
 Once incorporated within a system the following criteria are key to assessment of a given biometric for a specific application:
 Performance
 User Acceptance
 Resistance to Circumvention
Central Privacy, Sociological, and Legal Issues/Concerns
 System Design and Implementation must adequately address these issues to the satisfaction of the user, the law, and society.
 Is the biometric data like personal information (e.g. such as medical information) ?
 Can medical information be derived from the biometric data?
 Does the biometric system store information enabling a person’s “identity” to be reconstructed or stolen?
 Is permission received for any third party use of biometric information?
 What happens to the biometric data after the intended use is over?
 Is the security of the biometric data assured during transmission and storage?
 Contrast process of password loss or theft with that of a biometric.
 How is a theft detected and “new” biometric recognized?
 Notice of Biometric Use. Is the public aware a biometric system is being employed?
 Biometric System Design
 Target Design/Selection of Systems for:
 Acceptable overall performance for a given application
 Acceptable impact from a socio-legal perspective
 Examine the architecture of a biometric system, its subsystems, and their interaction
 Develop an understanding of design choices and tradeoffs in existing systems
 Build a framework to understand and quantify performance
Automated Biometric Identification: A Comprehensive View
 Biometric Systems Segment Organization
 Introduction
System Architecture
 System Architecture
 Application
 Authentication Vs. Identification
 Enrollment, Verification Modules
 Architecture Subsystems
Biometric Applications
Four general classes:
 Access (Cooperative, known subject)
 Logical Access (Access to computer networks, systems, or files)
 Physical Access (access to physical places or resources)
 Transaction Logging
 Surveillance (Non-cooperative, known subject)